Update README.md

README.md

@@ -1,9 +1,23 @@
 ---
 license: mit
-library_name: transformers
+library_name: exllamav2
 pipeline_tag: text-generation
+base_model: ByteDance-Seed/Seed-Coder-8B-Base
 ---
-
+# Seed-Coder-8B-Base
+Original model: [Seed-Coder-8B-Base](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Base) by [ByteDance Seed](https://huggingface.co/ByteDance-Seed)
+
+## Quants
+[4bpw h6 (main)](https://huggingface.co/cgus/Seed-Coder-8B-Base/tree/main)  
+[4.5bpw h6](https://huggingface.co/cgus/Seed-Coder-8B-Base/tree/4.5bpw-h6)  
+[5bpw h6](https://huggingface.co/cgus/Seed-Coder-8B-Base/tree/5bpw-h6)  
+[6bpw h6](https://huggingface.co/cgus/Seed-Coder-8B-Base/tree/6bpw-h6)  
+[8bpw h8](https://huggingface.co/cgus/Seed-Coder-8B-Base/tree/8bpw-h8)  
+## Quantization notes
+Made with Exllamav2 0.3.1 with default dataset.  
+These quants require a Nvidia RTX GPU on Windows or RTX/AMD ROCm on Linux and can be used with TabbyAPI or Text-Generation-WebUI.  
+Since it's Base model, it's mostly useful for text completion via v1/completions for code completion to be used in apps like VS Code + Continue.Dev.
+# Original model card
 # Seed-Coder-8B-Base
 
 <div align="left" style="line-height: 1;">